mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
parent
428bae66b5
commit
14d9007efd
2
.github/contributors/himkt.md
vendored
2
.github/contributors/himkt.md
vendored
|
@ -101,6 +101,6 @@ mark both statements:
|
||||||
| Name | himkt |
|
| Name | himkt |
|
||||||
| Company name (if applicable) | University of Tsukuba |
|
| Company name (if applicable) | University of Tsukuba |
|
||||||
| Title or role (if applicable) | |
|
| Title or role (if applicable) | |
|
||||||
| Date | 2018-06-08 |
|
| Date | 2018-06-07 |
|
||||||
| GitHub username | himkt |
|
| GitHub username | himkt |
|
||||||
| Website (optional) | https://himkt.github.io |
|
| Website (optional) | https://himkt.github.io |
|
||||||
|
|
|
@ -60,9 +60,8 @@ def detailed_tokens(tokenizer, text):
|
||||||
parts = node.feature.split(',')
|
parts = node.feature.split(',')
|
||||||
pos = ','.join(parts[0:4])
|
pos = ','.join(parts[0:4])
|
||||||
|
|
||||||
if len(parts) > 6:
|
if len(parts) > 7:
|
||||||
# this information is only available for words in the tokenizer dictionary
|
# this information is only available for words in the tokenizer dictionary
|
||||||
reading = parts[6]
|
|
||||||
base = parts[7]
|
base = parts[7]
|
||||||
|
|
||||||
words.append( ShortUnitWord(surface, base, pos) )
|
words.append( ShortUnitWord(surface, base, pos) )
|
||||||
|
|
Loading…
Reference in New Issue
Block a user